Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1747 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1535598 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1353199 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7136. Min Act: 0.0000

Data Index: 1812744 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1030560 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1861502 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1980421 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1490149 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1828997 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5539. Min Act: -0.0000

Data Index: 334788 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1894253 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5175. Min Act: -0.0000

Data Index: 427072 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1916418 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5261. Min Act: -0.0000

Data Index: 948864 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5253. Min Act: -0.0000

Data Index: 229182 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1103322 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5001. Min Act: -0.0000

Data Index: 728675 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1938228 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1264904 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.4685. Min Act: -0.0000

Data Index: 402062 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.4865. Min Act: -0.0000

Data Index: 670507 (The Pile)

Max Activating Token Index: 832